app.py

import gradio as gr

gr.Interface.load("tiiuae/falcon-40b").launch()


# import gradio as gr

# from transformers import AutoTokenizer, AutoModelForCausalLM
# import transformers
# import torch


# def falcon(input_text):
#     model = "tiiuae/falcon-40b"

#     tokenizer = AutoTokenizer.from_pretrained(model)
#     pipeline = transformers.pipeline(
#         "text-generation",
#         model=model,
#         tokenizer=tokenizer,
#         torch_dtype=torch.bfloat16,
#         trust_remote_code=True,
#         device_map="auto",
#     )
#     sequences = pipeline(
#         input_text, # "Was ist das höchste Gebäude in der Welt?"
#         max_length=200,
#         do_sample=True,
#         top_k=10,
#         num_return_sequences=1,
#         eos_token_id=tokenizer.eos_token_id,
#     )
#     for seq in sequences:
#         print(f"Result: {seq['generated_text']}")

#     return sequences[0]['generated_text']

# iface = gr.Interface(fn=falcon, inputs="text", outputs="text")
# iface.launch() # To create a public link, set `share=True`